Refined Analysis of FPL for Adversarial Markov Decision Processes

by   Yuanhao Wang, et al.

We consider the adversarial Markov Decision Process (MDP) problem, where the rewards for the MDP can be adversarially chosen, and the transition function can be either known or unknown. In both settings, Follow-the-PerturbedLeader (FPL) based algorithms have been proposed in previous literature. However, the established regret bounds for FPL based algorithms are worse than algorithms based on mirrordescent. We improve the analysis of FPL based algorithms in both settings, matching the current best regret bounds using faster and simpler algorithms.


page 1

page 2

page 3

page 4


A Bayesian Approach to Learning Bandit Structure in Markov Decision Processes

In the reinforcement learning literature, there are many algorithms deve...

Online Convex Optimization in Adversarial Markov Decision Processes

We consider online learning in episodic loop-free Markov decision proces...

Of Cores: A Partial-Exploration Framework for Markov Decision Processes

We introduce a framework for approximate analysis of Markov decision pro...

Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

We study minimax optimal reinforcement learning in episodic factored Mar...

The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition

We consider the best-of-both-worlds problem for learning an episodic Mar...

Improved Algorithms for Misspecified Linear Markov Decision Processes

For the misspecified linear Markov decision process (MLMDP) model of Jin...

On Low-Complexity Quickest Intervention of Mutated Diffusion Processes Through Local Approximation

We consider the problem of controlling a mutated diffusion process with ...